deepdoctection 0.43.6__tar.gz → 0.44.0__tar.gz

{deepdoctection-0.43.6 → deepdoctection-0.44.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deepdoctection
-Version: 0.43.6
+Version: 0.44.0
 Summary: Repository for Document AI
 Home-page: https://github.com/deepdoctection/deepdoctection
 Author: Dr. Janis Meyer

{deepdoctection-0.43.6 → deepdoctection-0.44.0}/deepdoctection/__init__.py

@@ -25,7 +25,7 @@ from .utils.logger import LoggingRecord, logger
 
 # pylint: enable=wrong-import-position
 
-__version__ = "0.43.6"
+__version__ = "0.44.0"
 
 _IMPORT_STRUCTURE = {
     "analyzer": ["config_sanity_checks", "get_dd_analyzer", "ServiceFactory"],
@@ -92,6 +92,7 @@ _IMPORT_STRUCTURE = {
         "convert_pdf_bytes_to_np_array_v2",
         "as_dict",
         "ImageAnnotationBaseView",
+        "MetaAnnotation",
         "Image",
         "Word",
         "Layout",
@@ -105,6 +106,7 @@ _IMPORT_STRUCTURE = {
         "DatasetAdapter",
         "DatasetBase",
         "MergeDataset",
+        "DatasetCard",
         "CustomDataset",
         "DataFlowBaseBuilder",
         "DatasetInfo",

{deepdoctection-0.43.6 → deepdoctection-0.44.0}/deepdoctection/datapoint/__init__.py

@@ -34,5 +34,5 @@ After all, the point here is not to provide an optimal processing environment.
 from .annotation import *
 from .box import *
 from .convert import *
-from .image import Image
+from .image import Image, MetaAnnotation
 from .view import *

{deepdoctection-0.43.6 → deepdoctection-0.44.0}/deepdoctection/datapoint/image.py

@@ -25,7 +25,7 @@ from collections import defaultdict
 from dataclasses import dataclass, field
 from os import environ, fspath
 from pathlib import Path
-from typing import Any, Optional, Sequence, Union, no_type_check
+from typing import Any, Optional, Sequence, TypedDict, Union, no_type_check
 
 import numpy as np
 from numpy import uint8
@@ -40,6 +40,54 @@ from .box import crop_box_from_image, global_to_local_coords, intersection_box
 from .convert import as_dict, convert_b64_to_np_array, convert_np_array_to_b64, convert_pdf_bytes_to_np_array_v2
 
 
+class MetaAnnotationDict(TypedDict):
+    """MetaAnnotationDict"""
+    image_annotations: list[str]
+    sub_categories: dict[str, dict[str, list[str]]]
+    relationships: dict[str, list[str]]
+    summaries: list[str]
+
+
+@dataclass(frozen=True)
+class MetaAnnotation:
+    """
+    An immutable dataclass that stores information about what `Image` are being
+    modified through a pipeline component.
+
+    Attributes:
+        image_annotations: Tuple of `ObjectTypes` representing image annotations.
+        sub_categories: Dictionary mapping `ObjectTypes` to dicts of `ObjectTypes` to sets of `ObjectTypes`
+        for sub-categories.
+        relationships: Dictionary mapping `ObjectTypes` to sets of `ObjectTypes` for relationships.
+        summaries: Tuple of `ObjectTypes` representing summaries.
+    """
+
+    image_annotations: tuple[ObjectTypes, ...] = field(default=())
+    sub_categories: dict[ObjectTypes, dict[ObjectTypes, set[ObjectTypes]]] = field(default_factory=dict)
+    relationships: dict[ObjectTypes, set[ObjectTypes]] = field(default_factory=dict)
+    summaries: tuple[ObjectTypes, ...] = field(default=())
+
+    def as_dict(self) -> MetaAnnotationDict:
+        """
+        Returns the MetaAnnotation as a dictionary, with all `ObjectTypes` converted to strings.
+
+        Returns:
+            A dictionary representation of the MetaAnnotation where all `ObjectTypes` are converted to strings.
+        """
+        return {
+            "image_annotations": [obj.value for obj in self.image_annotations],
+            "sub_categories": {
+                outer_key.value: {
+                    inner_key.value: [val.value for val in inner_values]
+                    for inner_key, inner_values in outer_value.items()
+                }
+                for outer_key, outer_value in self.sub_categories.items()
+            },
+            "relationships": {key.value: [val.value for val in values] for key, values in self.relationships.items()},
+            "summaries": [obj.value for obj in self.summaries],
+        }
+
+
 @dataclass
 class Image:
     """

{deepdoctection-0.43.6 → deepdoctection-0.44.0}/deepdoctection/datapoint/view.py

@@ -590,14 +590,16 @@ class Table(Layout):
 
     @property
     def csv_(self) -> list[list[list[Text_]]]:
+        """
+        Returns:
+            A csv-style representation of a table as list of lists of cell.text_.
+        """
         cells = self.cells
         table_list = [[[] for _ in range(self.number_of_columns)] for _ in range(self.number_of_rows)]  # type: ignore
         for cell in cells:
             table_list[cell.row_number - 1][cell.column_number - 1].append(cell.text_)  # type: ignore
         return table_list
 
-
-
     def __str__(self) -> str:
         out = " ".join([" ".join(row + ["\n"]) for row in self.csv])
         return out

{deepdoctection-0.43.6 → deepdoctection-0.44.0}/deepdoctection/datasets/base.py

@@ -25,14 +25,15 @@ import os
 import pprint
 from abc import ABC, abstractmethod
 from collections import defaultdict
+from dataclasses import dataclass, field
 from inspect import signature
 from pathlib import Path
-from typing import Any, Mapping, Optional, Sequence, Type, Union
+from typing import Any, Mapping, Optional, Sequence, Type, TypedDict, Union
 
 import numpy as np
 
 from ..dataflow import CacheData, ConcatData, CustomDataFromList, DataFlow
-from ..datapoint.image import Image
+from ..datapoint.image import Image, MetaAnnotation
 from ..utils.logger import LoggingRecord, logger
 from ..utils.settings import DatasetType, ObjectTypes, TypeOrStr, get_type
 from ..utils.types import PathLikeOrStr
@@ -405,6 +406,193 @@ class MergeDataset(DatasetBase):
         self._dataflow_builder.categories = self._categories()
 
 
+class DatasetCardDict(TypedDict):
+    """DatasetCardDict"""
+    name: str
+    dataset_type: Union[str, Any]
+    location: str
+    init_categories: Sequence[Any]
+    init_sub_categories: dict[Any, dict[Any, list[Any]]]
+    annotation_files: Optional[dict[Any, Union[Any, Sequence[Any]]]]
+    description: str
+    service_id_to_meta_annotation: dict[str, Any]
+
+
+# Usage:
+# def as_dict(self, ...) -> DatasetCardDict:
+
+
+@dataclass
+class DatasetCard:
+    """
+    An immutable dataclass representing the metadata of a dataset, including categories, sub-categories,
+    storage location, annotation files, and description. It facilitates management and consistency checks
+    for annotations generated by pipeline components.
+
+    Attributes:
+        name: Name of the dataset.
+        dataset_type: Type of the dataset as `ObjectTypes`.
+        location: Storage location of the dataset as `Path`.
+        init_categories: List of all initial categories (`ObjectTypes`) present in the dataset.
+        init_sub_categories: Mapping from main categories to sub-categories and their possible values.
+        annotation_files: Optional mapping from split names to annotation files.
+        description: Description of the dataset.
+        service_id_to_meta_annotation: Mapping from service IDs to `MetaAnnotation` objects, storing
+            annotation structure for different pipeline components.
+    """
+
+    name: str
+    dataset_type: ObjectTypes
+    location: Path
+    init_categories: list[ObjectTypes] = field(default_factory=list)
+    init_sub_categories: dict[ObjectTypes, dict[ObjectTypes, list[ObjectTypes]]] = field(default_factory=dict)
+    annotation_files: Optional[Mapping[str, Union[str, Sequence[str]]]] = None
+    description: str = field(default="")
+    service_id_to_meta_annotation: dict[str, MetaAnnotation] = field(default_factory=dict)
+
+    def save_dataset_card(self, file_path: Union[str, Path]) -> None:
+        """Save the DatasetCard instance as a JSON file."""
+        with open(file_path, "w", encoding="utf-8") as f:
+            json.dump(self.as_dict(), f, indent=4)
+
+    @staticmethod
+    def load_dataset_card(file_path: PathLikeOrStr) -> DatasetCard:
+        """Load a DatasetCard instance from a JSON file."""
+        with open(file_path, "r", encoding="utf-8") as f:
+            data = json.load(f)
+            service_id_to_meta_annotation = {}
+            if "service_id_to_meta_annotation" in data:
+                for service_id, meta_ann_dict in data.pop("service_id_to_meta_annotation").items():
+                    meta_ann_dict["image_annotations"] = tuple(
+                        get_type(cat) for cat in meta_ann_dict["image_annotations"]
+                    )
+                    meta_ann_dict["sub_categories"] = {
+                        get_type(cat): {
+                            get_type(sub_cat): set({get_type(value) for value in values})
+                            for sub_cat, values in sub_cats.items()
+                        }
+                        for cat, sub_cats in meta_ann_dict["sub_categories"].items()
+                    }
+                    meta_ann_dict["relationships"] = {
+                        get_type(key): set({get_type(value) for value in values})
+                        for key, values in meta_ann_dict["relationships"].items()
+                    }
+                    meta_ann_dict["summaries"] = tuple(get_type(val) for val in meta_ann_dict["summaries"])
+                    service_id_to_meta_annotation[service_id] = MetaAnnotation(**meta_ann_dict)
+                data["service_id_to_meta_annotation"] = service_id_to_meta_annotation
+        return DatasetCard(**data)
+
+    def as_dict(self, keep_object_types: bool = False) -> DatasetCardDict:
+        """Convert the DatasetCard to a dictionary."""
+        if keep_object_types:
+            return {
+                "name": self.name,
+                "dataset_type": self.dataset_type,
+                "location": self.location.as_posix(),
+                "init_categories": self.init_categories,
+                "init_sub_categories": self.init_sub_categories,
+                "annotation_files": self.annotation_files,  # type: ignore
+                "description": self.description,
+                "service_id_to_meta_annotation": {
+                    key: val.as_dict() for key, val in self.service_id_to_meta_annotation.items()
+                },
+            }
+        return {
+            "name": self.name,
+            "dataset_type": self.dataset_type.value,
+            "location": self.location.as_posix(),
+            "init_categories": [cat.value for cat in self.init_categories],
+            "init_sub_categories": {
+                cat.value: {
+                    sub_cat.value: list({value.value for value in values}) for sub_cat, values in sub_cats.items()
+                }
+                for cat, sub_cats in self.init_sub_categories.items()
+            },
+            "annotation_files": self.annotation_files,  # type: ignore
+            "description": self.description,
+            "service_id_to_meta_annotation": {
+                key: val.as_dict() for key, val in self.service_id_to_meta_annotation.items()
+            },
+        }
+
+    def update_from_pipeline(
+        self, meta_annotations: MetaAnnotation, service_id_to_meta_annotation: Mapping[str, MetaAnnotation]
+    ) -> None:
+        """
+        Update the initial categories, sub-categories, and service ID to `MetaAnnotation` mapping
+        based on the results from a pipeline.
+
+        ```python
+           analyzer = dd.get_dd_analyzer(config_overwrite=["USE_OCR=True","USE_TABLE_SEGMENTATION=True"])
+           meta_annotations = analyzer.get_meta_annotation()
+           service_id_to_meta_annotation = analyzer.get_service_id_to_meta_annotation()
+           card.update_from_pipeline(meta_annotations, service_id_to_meta_annotation)
+        ```
+
+        Args:
+            meta_annotations: A `MetaAnnotation` object containing new or updated categories and sub-categories.
+            service_id_to_meta_annotation: A mapping from service IDs to `MetaAnnotation` objects generated by the
+             pipeline.
+
+        Adds any missing categories, sub-categories, and values to the respective attributes of the instance.
+        """
+        for category in meta_annotations.image_annotations:
+            if category not in self.init_categories:
+                self.init_categories.append(category)
+        for cat, sub_cats in meta_annotations.sub_categories.items():
+            if cat not in self.init_sub_categories:
+                self.init_sub_categories[cat] = {}
+            for sub_cat, values in sub_cats.items():
+                if sub_cat not in self.init_sub_categories[cat]:
+                    self.init_sub_categories[cat][sub_cat] = []
+                for value in values:
+                    if value not in self.init_sub_categories[cat][sub_cat]:
+                        self.init_sub_categories[cat][sub_cat].append(value)
+
+        for service_id, meta_annotation in service_id_to_meta_annotation.items():
+            if service_id not in self.service_id_to_meta_annotation:
+                self.service_id_to_meta_annotation[service_id] = meta_annotation
+
+    def __post_init__(self) -> None:
+        """
+        Perform internal consistency checks ensuring `init_categories` and
+        `init_sub_categories` align with `service_id_to_meta_annotation`.
+        """
+        self.dataset_type = get_type(self.dataset_type)
+        self.location = Path(self.location)
+        self.init_categories = [get_type(cat) for cat in self.init_categories]
+        self.init_sub_categories = {
+            get_type(outer_key): {
+                get_type(inner_key): [get_type(value) for value in inner_values]
+                for inner_key, inner_values in outer_value.items()
+            }
+            for outer_key, outer_value in self.init_sub_categories.items()
+        }
+
+        if self.service_id_to_meta_annotation is None:
+            return
+
+        # Check compatibility of image_annotations with init_categories
+        for service_id, meta_annotation in self.service_id_to_meta_annotation.items():
+            for annotation in meta_annotation.image_annotations:
+                if annotation not in self.init_categories:
+                    raise ValueError(
+                        f"Image annotation '{annotation}' in service ID '{service_id}' is not "
+                        f"present in `init_categories`."
+                    )
+
+            # Check compatibility of sub_categories
+            for cat, sub_cats in meta_annotation.sub_categories.items():
+                if not (
+                    cat in self.init_sub_categories
+                    and all(sub_cat in self.init_sub_categories[cat] for sub_cat in sub_cats)
+                ):
+                    raise ValueError(
+                        f"Sub-categories for category '{cat}' in service ID '{service_id}' "
+                        f"do not match with `init_sub_categories`."
+                    )
+
+
 class CustomDataset(DatasetBase):
     """
     A simple dataset interface that implements the boilerplate code and reduces complexity by merely leaving
@@ -512,53 +700,9 @@ class CustomDataset(DatasetBase):
         Returns:
             A CustomDataset instance created from the dataset card.
         """
-
-        with open(file_path, "r", encoding="UTF-8") as file:
-            meta_data = json.load(file)
-        meta_data["dataset_type"] = get_type(meta_data["dataset_type"])
-        meta_data["location"] = Path(meta_data["location"])
-        meta_data["init_categories"] = [get_type(cat) for cat in meta_data["init_categories"]]
-        meta_data["init_sub_categories"] = (
-            {
-                get_type(cat): {
-                    get_type(sub_cat_key): [get_type(sub_cat_value) for sub_cat_value in sub_cat_values]
-                    for sub_cat_key, sub_cat_values in sub_cats.items()
-                }
-                for cat, sub_cats in meta_data["init_sub_categories"].items()
-            }
-            if meta_data["init_sub_categories"] is not None
-            else None
+        dataset_card = DatasetCard.load_dataset_card(file_path)
+        dataset_card_as_dict = dataset_card.as_dict(True)
+        dataset_card_as_dict.pop("service_id_to_meta_annotation")  # type: ignore  # pylint: disable=E1123
+        return CustomDataset(  # pylint: disable=E1123
+            **dataset_card_as_dict, dataflow_builder=dataflow_builder  # type: ignore
         )
-        return CustomDataset(**meta_data, dataflow_builder=dataflow_builder)
-
-    def as_dict(self) -> Mapping[str, Any]:
-        """
-        Return:
-           The meta-data of the dataset as a dictionary.
-        """
-        return {
-            "name": self.name,
-            "dataset_type": self.type,
-            "location": str(self.location),
-            "annotation_files": self.annotation_files,
-            "init_categories": [cat.value for cat in self.init_categories],
-            "init_sub_categories": {
-                cat.value: {
-                    sub_cat_key.value: [sub_cat_value.value for sub_cat_value in sub_cat_values]
-                    for sub_cat_key, sub_cat_values in sub_cats.items()
-                }
-                for cat, sub_cats in self.init_sub_categories.items()
-            }
-            if self.init_sub_categories is not None
-            else None,
-        }
-
-    def save_dataset_card(self, file_path: str) -> None:
-        """
-        Save the dataset card to a `JSON` file.
-
-        Args:
-            file_path: file_path
-        """
-        with open(file_path, "w", encoding="UTF-8") as file:
-            json.dump(self.as_dict(), file, indent=4)

{deepdoctection-0.43.6 → deepdoctection-0.44.0}/deepdoctection/pipe/base.py

@@ -23,12 +23,11 @@ from __future__ import annotations
 
 from abc import ABC, abstractmethod
 from collections import defaultdict
-from dataclasses import dataclass, field
 from typing import Any, Callable, Mapping, Optional, Union
 from uuid import uuid1
 
 from ..dataflow import DataFlow, MapData
-from ..datapoint.image import Image
+from ..datapoint.image import Image, MetaAnnotation
 from ..mapper.misc import curry
 from ..utils.context import timed_operation
 from ..utils.identifier import get_uuid_from_str
@@ -37,25 +36,6 @@ from ..utils.types import DP
 from .anngen import DatapointManager
 
 
-@dataclass(frozen=True)
-class MetaAnnotation:
-    """
-    A immutable dataclass that stores information about what `Image` are being
-    modified through a pipeline component.
-
-    Attributes:
-        image_annotations: Tuple of `ObjectTypes` representing image annotations.
-        sub_categories: Dictionary mapping `ObjectTypes` to sets of `ObjectTypes` for sub-categories.
-        relationships: Dictionary mapping `ObjectTypes` to sets of `ObjectTypes` for relationships.
-        summaries: Tuple of `ObjectTypes` representing summaries.
-    """
-
-    image_annotations: tuple[ObjectTypes, ...] = field(default=())
-    sub_categories: dict[ObjectTypes, set[ObjectTypes]] = field(default_factory=dict)
-    relationships: dict[ObjectTypes, set[ObjectTypes]] = field(default_factory=dict)
-    summaries: tuple[ObjectTypes, ...] = field(default=())
-
-
 class PipelineComponent(ABC):
     """
     Base class for pipeline components.
@@ -427,15 +407,24 @@ class Pipeline(ABC):
             as well as summaries (list with sub categories).
         """
         image_annotations: list[ObjectTypes] = []
-        sub_categories = defaultdict(set)
-        relationships = defaultdict(set)
+        sub_categories: dict[ObjectTypes, dict[ObjectTypes, set[ObjectTypes]]] = {}
+        relationships = defaultdict(set[ObjectTypes])  # type: ignore
         summaries: list[ObjectTypes] = []
         for component in self.pipe_component_list:
             meta_anns = component.get_meta_annotation()
             image_annotations.extend(meta_anns.image_annotations)
             for key, value in meta_anns.sub_categories.items():
-                sub_categories[key].update(value)
-            for key, value in meta_anns.relationships.items():
+                sub_dict = meta_anns.sub_categories[key]
+                for sub_cat, sub_cat_value in value.items():
+                    if sub_cat in sub_dict:
+                        sub_dict[sub_cat].update(sub_cat_value)
+                    else:
+                        sub_dict[sub_cat] = {sub_cat_value}  # type: ignore
+                if key in sub_categories:
+                    sub_categories[key].update(sub_dict)
+                else:
+                    sub_categories[key] = sub_dict
+            for key, value in meta_anns.relationships.items():  # type: ignore
                 relationships[key].update(value)
             summaries.extend(meta_anns.summaries)
         return MetaAnnotation(
@@ -445,6 +434,21 @@ class Pipeline(ABC):
             summaries=tuple(summaries),
         )
 
+    def get_service_id_to_meta_annotation(self) -> Mapping[str, MetaAnnotation]:
+        """
+        Collects meta annotations from all pipeline components and return a dict of service id to its meta annotation.
+
+        Returns:
+            `service_id` to `MetaAnnotation` with information about image annotations (list), sub categories (dict with
+            category names and generated sub categories), relationships (dict with category names and generated
+            relationships) as well as summaries (list with sub categories).
+        """
+        service_id_to_meta_annotation = {}
+        for component in self.pipe_component_list:
+            meta_anns = component.get_meta_annotation()
+            service_id_to_meta_annotation[component.service_id] = meta_anns
+        return service_id_to_meta_annotation
+
     def get_pipeline_info(
         self, service_id: Optional[str] = None, name: Optional[str] = None
     ) -> Union[str, Mapping[str, str]]:

{deepdoctection-0.43.6 → deepdoctection-0.44.0}/deepdoctection/pipe/common.py

@@ -28,13 +28,13 @@ from typing import Literal, Mapping, Optional, Sequence, Union
 import numpy as np
 
 from ..dataflow import DataFlow, MapData
-from ..datapoint.image import Image
+from ..datapoint.image import Image, MetaAnnotation
 from ..datapoint.view import IMAGE_DEFAULTS, Page
 from ..extern.base import DetectionResult
 from ..mapper.match import match_anns_by_distance, match_anns_by_intersection
 from ..mapper.misc import to_image
 from ..utils.settings import LayoutType, ObjectTypes, Relationships, TypeOrStr, get_type
-from .base import MetaAnnotation, PipelineComponent
+from .base import PipelineComponent
 from .registry import pipeline_component_registry
 
 if os.environ.get("DD_USE_TORCH"):

{deepdoctection-0.43.6 → deepdoctection-0.44.0}/deepdoctection/pipe/concurrency.py

@@ -29,11 +29,11 @@ from typing import Callable, Optional, Sequence, Union
 import tqdm
 
 from ..dataflow import DataFlow, MapData
-from ..datapoint.image import Image
+from ..datapoint.image import Image, MetaAnnotation
 from ..utils.context import timed_operation
 from ..utils.tqdm import get_tqdm
 from ..utils.types import QueueType, TqdmType
-from .base import MetaAnnotation, PipelineComponent
+from .base import PipelineComponent
 from .common import ImageParsingService, PageParsingService
 from .registry import pipeline_component_registry
 

{deepdoctection-0.43.6 → deepdoctection-0.44.0}/deepdoctection/pipe/language.py

@@ -20,12 +20,12 @@ Module for language detection pipeline component
 """
 from typing import Optional, Sequence
 
-from ..datapoint.image import Image
+from ..datapoint.image import Image, MetaAnnotation
 from ..datapoint.view import ImageDefaults, Page
 from ..extern.base import LanguageDetector, ObjectDetector
 from ..utils.error import ImageError
 from ..utils.settings import PageType, TypeOrStr, get_type
-from .base import MetaAnnotation, PipelineComponent
+from .base import PipelineComponent
 from .registry import pipeline_component_registry
 
 

{deepdoctection-0.43.6 → deepdoctection-0.44.0}/deepdoctection/pipe/layout.py

@@ -24,13 +24,13 @@ from typing import Optional, Sequence, Union
 
 import numpy as np
 
-from ..datapoint.image import Image
+from ..datapoint.image import Image, MetaAnnotation
 from ..extern.base import ObjectDetector, PdfMiner
 from ..mapper.misc import curry
 from ..utils.error import ImageError
 from ..utils.settings import ObjectTypes
 from ..utils.transform import PadTransform
-from .base import MetaAnnotation, PipelineComponent
+from .base import PipelineComponent
 from .registry import pipeline_component_registry
 
 

{deepdoctection-0.43.6 → deepdoctection-0.44.0}/deepdoctection/pipe/lm.py

@@ -23,11 +23,11 @@ from __future__ import annotations
 from copy import copy
 from typing import TYPE_CHECKING, Any, Callable, Literal, Optional, Sequence, Union
 
-from ..datapoint.image import Image
+from ..datapoint.image import Image, MetaAnnotation
 from ..extern.base import SequenceClassResult
 from ..mapper.laylmstruct import image_to_layoutlm_features, image_to_lm_features
 from ..utils.settings import BioTag, LayoutType, ObjectTypes, PageType, TokenClasses, WordType
-from .base import MetaAnnotation, PipelineComponent
+from .base import PipelineComponent
 from .registry import pipeline_component_registry
 
 if TYPE_CHECKING:
@@ -246,7 +246,17 @@ class LMTokenClassifierService(PipelineComponent):
     def get_meta_annotation(self) -> MetaAnnotation:
         return MetaAnnotation(
             image_annotations=(),
-            sub_categories={LayoutType.WORD: {WordType.TOKEN_CLASS, WordType.TAG, WordType.TOKEN_TAG}},
+            sub_categories={
+                LayoutType.WORD: {
+                    WordType.TOKEN_CLASS: set(self.language_model.categories.categories_semantics)  # type: ignore
+                    if self.language_model.categories.categories_semantics
+                    else [],
+                    WordType.TAG: set(self.language_model.categories.categories_bio)  # type: ignore
+                    if self.language_model.categories.categories_bio
+                    else [],
+                    WordType.TOKEN_TAG: set(self.language_model.categories.get_categories(as_dict=False)),
+                }
+            },
             relationships={},
             summaries=(),
         )

{deepdoctection-0.43.6 → deepdoctection-0.44.0}/deepdoctection/pipe/order.py

@@ -31,11 +31,11 @@ import numpy as np
 
 from ..datapoint.annotation import ImageAnnotation
 from ..datapoint.box import BoundingBox, merge_boxes
-from ..datapoint.image import Image
+from ..datapoint.image import Image, MetaAnnotation
 from ..datapoint.view import IMAGE_DEFAULTS
 from ..extern.base import DetectionResult
 from ..extern.tp.tpfrcnn.utils.np_box_ops import ioa as np_ioa
-from ..pipe.base import MetaAnnotation, PipelineComponent
+from ..pipe.base import PipelineComponent
 from ..pipe.registry import pipeline_component_registry
 from ..utils.logger import LoggingRecord, logger
 from ..utils.settings import LayoutType, ObjectTypes, Relationships, TypeOrStr, get_type
@@ -611,8 +611,8 @@ class TextLineService(TextLineServiceMixin):
         """
         return MetaAnnotation(
             image_annotations=(LayoutType.LINE,),
-            sub_categories={LayoutType.LINE: {Relationships.CHILD}},
-            relationships={},
+            sub_categories={},
+            relationships={LayoutType.LINE: {Relationships.CHILD}},
             summaries=(),
         )
 
@@ -818,7 +818,11 @@ class TextOrderService(TextLineServiceMixin):
         anns_with_reading_order = list(copy(self.floating_text_block_categories)) + add_category
         return MetaAnnotation(
             image_annotations=tuple(image_annotations),
-            sub_categories={category: {Relationships.READING_ORDER} for category in anns_with_reading_order},
+            sub_categories={  # type: ignore
+                category: {Relationships.READING_ORDER: {Relationships.READING_ORDER}}
+                for category in anns_with_reading_order
+            }
+            | {self.text_container: {Relationships.READING_ORDER: {Relationships.READING_ORDER}}},
             relationships={},
             summaries=(),
         )

{deepdoctection-0.43.6 → deepdoctection-0.44.0}/deepdoctection/pipe/refine.py

@@ -31,12 +31,12 @@ import networkx as nx  # type: ignore
 
 from ..datapoint.annotation import ImageAnnotation
 from ..datapoint.box import merge_boxes
-from ..datapoint.image import Image
+from ..datapoint.image import Image, MetaAnnotation
 from ..extern.base import DetectionResult
 from ..mapper.maputils import MappingContextManager
 from ..utils.error import ImageError
 from ..utils.settings import CellType, LayoutType, ObjectTypes, Relationships, TableType, get_type
-from .base import MetaAnnotation, PipelineComponent
+from .base import PipelineComponent
 from .registry import pipeline_component_registry
 
 __all__ = ["TableSegmentationRefinementService", "generate_html_string"]
@@ -537,12 +537,12 @@ class TableSegmentationRefinementService(PipelineComponent):
             image_annotations=(),
             sub_categories={
                 LayoutType.CELL: {
-                    CellType.ROW_NUMBER,
-                    CellType.COLUMN_NUMBER,
-                    CellType.ROW_SPAN,
-                    CellType.COLUMN_SPAN,
+                    CellType.ROW_NUMBER: {CellType.ROW_NUMBER},
+                    CellType.COLUMN_NUMBER: {CellType.COLUMN_NUMBER},
+                    CellType.ROW_SPAN: {CellType.ROW_SPAN},
+                    CellType.COLUMN_SPAN: {CellType.COLUMN_SPAN},
                 },
-                LayoutType.TABLE: {TableType.HTML},
+                LayoutType.TABLE: {TableType.HTML: {TableType.HTML}},
             },
             relationships={},
             summaries=(),